Xiaojie Xu

Chuqin Geng, Nham Le, Xiaojie Xu et al.

Having reliable specifications is an unavoidable challenge in achieving verifiable correctness, robustness, and interpretability of AI systems. Existing specifications for neural networks are in the paradigm of data as specification. That is, the local neighborhood centering around a reference input is considered to be correct (or robust). While existing specifications contribute to verifying adversarial robustness, a significant problem in many research domains, our empirical study shows that those verified regions are somewhat tight, and thus fail to allow verification of test set inputs, making them impractical for some real-world applications. To this end, we propose a new family of specifications called neural representation as specification, which uses the intrinsic information of neural networks - neural activation patterns (NAPs), rather than input data to specify the correctness and/or robustness of neural network predictions. We present a simple statistical approach to mining neural activation patterns. To show the effectiveness of discovered NAPs, we formally verify several important properties, such as various types of misclassifications will never happen for a given NAP, and there is no ambiguity between different NAPs. We show that by using NAP, we can verify a significant region of the input space, while still recalling 84% of the data on MNIST. Moreover, we can push the verifiable bound to 10 times larger on the CIFAR10 benchmark. Thus, we argue that NAPs can potentially be used as a more reliable and extensible specification for neural network verification.

Junhao Su, Changpeng Cai, Feiyu Zhu et al.

Deep neural networks conventionally employ end-to-end backpropagation for their training process, which lacks biological credibility and triggers a locking dilemma during network parameter updates, leading to significant GPU memory use. Supervised local learning, which segments the network into multiple local blocks updated by independent auxiliary networks. However, these methods cannot replace end-to-end training due to lower accuracy, as gradients only propagate within their local block, creating a lack of information exchange between blocks. To address this issue and establish information transfer across blocks, we propose a Momentum Auxiliary Network (MAN) that establishes a dynamic interaction mechanism. The MAN leverages an exponential moving average (EMA) of the parameters from adjacent local blocks to enhance information flow. This auxiliary network, updated through EMA, helps bridge the informational gap between blocks. Nevertheless, we observe that directly applying EMA parameters has certain limitations due to feature discrepancies among local blocks. To overcome this, we introduce learnable biases, further boosting performance. We have validated our method on four image classification datasets (CIFAR-10, STL-10, SVHN, ImageNet), attaining superior performance and substantial memory savings. Notably, our method can reduce GPU memory usage by more than 45\% on the ImageNet dataset compared to end-to-end training, while achieving higher performance. The Momentum Auxiliary Network thus offers a new perspective for supervised local learning. Our code is available at: https://github.com/JunhaoSu0/MAN.

Junhao Su, Chenghao He, Feiyu Zhu et al.

Traditional deep learning relies on end-to-end backpropagation for training, but it suffers from drawbacks such as high memory consumption and not aligning with biological neural networks. Recent advancements have introduced locally supervised learning, which divides networks into modules with isolated gradients and trains them locally. However, this approach can lead to performance lag due to limited interaction between these modules, and the design of auxiliary networks occupies a certain amount of GPU memory. To overcome these limitations, we propose a novel model called HPFF that performs hierarchical locally supervised learning and patch-level feature computation on the auxiliary networks. Hierarchical Locally Supervised Learning (HiLo) enables the network to learn features at different granularity levels along their respective local paths. Specifically, the network is divided into two-level local modules: independent local modules and cascade local modules. The cascade local modules combine two adjacent independent local modules, incorporating both updates within the modules themselves and information exchange between adjacent modules. Patch Feature Fusion (PFF) reduces GPU memory usage by splitting the input features of the auxiliary networks into patches for computation. By averaging these patch-level features, it enhances the network's ability to focus more on those patterns that are prevalent across multiple patches. Furthermore, our method exhibits strong generalization capabilities and can be seamlessly integrated with existing techniques. We conduct experiments on CIFAR-10, STL-10, SVHN, and ImageNet datasets, and the results demonstrate that our proposed HPFF significantly outperforms previous approaches, consistently achieving state-of-the-art performance across different datasets. Our code is available at: https://github.com/Zeudfish/HPFF.

Ziqi Huang, Fan Zhang, Xiaojie Xu et al.

Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align with human perceptions; 2) An ideal evaluation system should provide insights to inform future developments of video generation. To this end, we present VBench, a comprehensive benchmark suite that dissects "video generation quality" into specific, hierarchical, and disentangled dimensions, each with tailored prompts and evaluation methods. VBench has several appealing properties: 1) Comprehensive Dimensions: VBench comprises 16 dimensions in video generation (e.g., subject identity inconsistency, motion smoothness, temporal flickering, and spatial relationship, etc). The evaluation metrics with fine-grained levels reveal individual models' strengths and weaknesses. 2) Human Alignment: We also provide a dataset of human preference annotations to validate our benchmarks' alignment with human perception, for each evaluation dimension respectively. 3) Valuable Insights: We look into current models' ability across various evaluation dimensions, and various content types. We also investigate the gaps between video and image generation models. 4) Versatile Benchmarking: VBench++ supports evaluating text-to-video and image-to-video. We introduce a high-quality Image Suite with an adaptive aspect ratio to enable fair evaluations across different image-to-video generation settings. Beyond assessing technical quality, VBench++ evaluates the trustworthiness of video generative models, providing a more holistic view of model performance. 5) Full Open-Sourcing: We fully open-source VBench++ and continually add new video generation models to our leaderboard to drive forward the field of video generation.

Chuqin Geng, Xiaojie Xu, Haolin Ye et al.

Just like weights, bias terms are the learnable parameters of many popular machine learning models, including neural networks. Biases are thought to enhance the representational power of neural networks, enabling them to solve a variety of tasks in computer vision. However, we argue that biases can be disregarded for some image-related tasks such as image classification, by considering the intrinsic distribution of images in the input space and desired model properties from first principles. Our findings suggest that zero-bias neural networks can perform comparably to biased networks for practical image classification tasks. We demonstrate that zero-bias neural networks possess a valuable property called scalar (multiplication) invariance. This means that the prediction of the network remains unchanged when the contrast of the input image is altered. We extend scalar invariance to more general cases, enabling formal verification of certain convex regions of the input space. Additionally, we prove that zero-bias neural networks are fair in predicting the zero image. Unlike state-of-the-art models that may exhibit bias toward certain labels, zero-bias networks have uniform belief in all labels. We believe dropping bias terms can be considered as a geometric prior in designing neural network architecture for image classification, which shares the spirit of adapting convolutions as the transnational invariance prior. The robustness and fairness advantages of zero-bias neural networks may also indicate a promising path towards trustworthy and ethical AI.

Fulong Ma, Xiaoyang Yan, Guoyang Zhao et al.

Monocular 3D object detection plays a crucial role in autonomous driving. However, existing monocular 3D detection algorithms depend on 3D labels derived from LiDAR measurements, which are costly to acquire for new datasets and challenging to deploy in novel environments. Specifically, this study investigates the pipeline for training a monocular 3D object detection model on a diverse collection of 3D and 2D datasets. The proposed framework comprises three components: (1) a robust monocular 3D model capable of functioning across various camera settings, (2) a selective-training strategy to accommodate datasets with differing class annotations, and (3) a pseudo 3D training approach using 2D labels to enhance detection performance in scenes containing only 2D labels. With this framework, we could train models on a joint set of various open 3D/2D datasets to obtain models with significantly stronger generalization capability and enhanced performance on new dataset with only 2D labels. We conduct extensive experiments on KITTI/nuScenes/ONCE/Cityscapes/BDD100K datasets to demonstrate the scaling ability of the proposed method.

Xiaofeng Mao, Zhen Li, Chuanhao Li et al.

Recent approaches have demonstrated the promise of using diffusion models to generate interactive and explorable worlds. However, most of these methods face critical challenges such as excessively large parameter sizes, reliance on lengthy inference steps, and rapidly growing historical context, which severely limit real-time performance and lack text-controlled generation capabilities. To address these challenges, we propose \method, a novel framework designed to generate realistic, interactive, and continuous worlds from a single image or text prompt. \method achieves this through a carefully designed framework that supports keyboard-based exploration of the generated worlds. The framework comprises three core components: (1) a long-video generation framework integrating unified context compression with linear attention; (2) a real-time streaming acceleration strategy powered by bidirectional attention distillation and an enhanced text embedding scheme; (3) a text-controlled method for generating world events. We have provided the codebase in the supplementary material.

Wenshuo Peng, Gongxuan Wang, Tianmeng Yang et al.

Recent text-to-video generation models exhibit remarkable progress in visual realism, motion fidelity, and text-video alignment, yet they remain fundamentally limited in their ability to generate socially coherent behavior. Unlike humans, who effortlessly infer intentions, beliefs, emotions, and social norms from brief visual cues, current models tend to render literal scenes without capturing the underlying causal or psychological logic. To systematically evaluate this gap, we introduce the first benchmark for social reasoning in video generation. Grounded in findings from developmental and social psychology, our benchmark organizes thirty classic social cognition paradigms into seven core dimensions, including mental-state inference, goal-directed action, joint attention, social coordination, prosocial behavior, social norms, and multi-agent strategy. To operationalize these paradigms, we develop a fully training-free agent-based pipeline that (i) distills the reasoning mechanism of each experiment, (ii) synthesizes diverse video-ready scenarios, (iii) enforces conceptual neutrality and difficulty control through cue-based critique, and (iv) evaluates generated videos using a high-capacity VLM judge across five interpretable dimensions of social reasoning. Using this framework, we conduct the first large-scale study across seven state-of-the-art video generation systems. Our results reveal substantial performance gaps: while modern models excel in surface-level plausibility, they systematically fail in intention recognition, belief reasoning, joint attention, and prosocial inference.

Zongyuan Li, Chang Lu, Xiaojie Xu et al.

Since the emergence of the Large Language Model (LLM), LLM has been widely used in fields such as writing, translating, and searching. However, there is still great potential for LLM-based methods in handling complex tasks such as decision-making in the StarCraft II environment. To address problems such as lack of relevant knowledge and poor control over subtasks of varying importance, we propose a Hierarchical Expert Prompt (HEP) for LLM. Our method improves the understanding of game situations through expert-level tactical knowledge, improving the processing quality of tasks of varying importance through a hierarchical framework. Our approach defeated the highest level (Elite) standard built-in agent in TextStarCraft II for the first time and consistently outperformed the baseline method in other difficulties. Our experiments suggest that the proposed method is a practical solution for tackling complex decision-making challenges. The replay video can be viewed on https://www.bilibili.com/video/BV1uz42187EF and https://youtu.be/dO3PshWLV5M, and our codes have been open-sourced on https://github.com/luchang1113/HEP-LLM-play-StarCraftII.

Xiaojie Xu, Tianshuo Xu, Fulong Ma et al.

We explore Bird's-Eye View (BEV) generation, converting a BEV map into its corresponding multi-view street images. Valued for its unified spatial representation aiding multi-sensor fusion, BEV is pivotal for various autonomous driving applications. Creating accurate street-view images from BEV maps is essential for portraying complex traffic scenarios and enhancing driving algorithms. Concurrently, diffusion-based conditional image generation models have demonstrated remarkable outcomes, adept at producing diverse, high-quality, and condition-aligned results. Nonetheless, the training of these models demands substantial data and computational resources. Hence, exploring methods to fine-tune these advanced models, like Stable Diffusion, for specific conditional generation tasks emerges as a promising avenue. In this paper, we introduce a practical framework for generating images from a BEV layout. Our approach comprises two main components: the Neural View Transformation and the Street Image Generation. The Neural View Transformation phase converts the BEV map into aligned multi-view semantic segmentation maps by learning the shape correspondence between the BEV and perspective views. Subsequently, the Street Image Generation phase utilizes these segmentations as a condition to guide a fine-tuned latent diffusion model. This finetuning process ensures both view and style consistency. Our model leverages the generative capacity of large pretrained diffusion models within traffic contexts, effectively yielding diverse and condition-coherent street view images.

Xiaojie Xu, Zhengyuan Lin, Kang He et al.

Interactive video generation models such as Genie, YUME, HY-World, and Matrix-Game are advancing rapidly, yet every model is evaluated on its own benchmark with private scenes and trajectories, making fair cross-model comparison impossible. Existing public benchmarks offer useful metrics such as trajectory error, aesthetic scores, and VLM-based judgments, but none supplies the standardized test conditions -- identical scenes, identical action sequences, and a unified control interface -- needed to make those metrics comparable across models with heterogeneous inputs. We introduce WorldMark, the first benchmark that provides such a common playing field for interactive Image-to-Video world models. WorldMark contributes: (1) a unified action-mapping layer that translates a shared WASD-style action vocabulary into each model's native control format, enabling apples-to-apples comparison across six major models on identical scenes and trajectories; (2) a hierarchical test suite of 500 evaluation cases covering first- and third-person viewpoints, photorealistic and stylized scenes, and three difficulty tiers from Easy to Hard spanning 20-60s; and (3) a modular evaluation toolkit for Visual Quality, Control Alignment, and World Consistency, designed so that researchers can reuse our standardized inputs while plugging in their own metrics as the field evolves. We will release all data, evaluation code, and model outputs to facilitate future research. Beyond offline metrics, we launch World Model Arena (warena.ai), an online platform where anyone can pit leading world models against each other in side-by-side battles and watch the live leaderboard.

Haoyu Chen, Xiaojie Xu, Wenbo Li et al.

Poster design is a critical medium for visual communication. Prior work has explored automatic poster design using deep learning techniques, but these approaches lack text accuracy, user customization, and aesthetic appeal, limiting their applicability in artistic domains such as movies and exhibitions, where both clear content delivery and visual impact are essential. To address these limitations, we present POSTA: a modular framework powered by diffusion models and multimodal large language models (MLLMs) for customized artistic poster generation. The framework consists of three modules. Background Diffusion creates a themed background based on user input. Design MLLM then generates layout and typography elements that align with and complement the background style. Finally, to enhance the poster's aesthetic appeal, ArtText Diffusion applies additional stylization to key text elements. The final result is a visually cohesive and appealing poster, with a fully modular process that allows for complete customization. To train our models, we develop the PosterArt dataset, comprising high-quality artistic posters annotated with layout, typography, and pixel-level stylized text segmentation. Our comprehensive experimental analysis demonstrates POSTA's exceptional controllability and design diversity, outperforming existing models in both text accuracy and aesthetic quality.

Zongyuan Li, Yanan Ni, Runnan Qi et al.

The tremendous potential has been demonstrated by large language models (LLMs) in intelligent decision-making problems, with unprecedented capabilities shown across diverse applications ranging from gaming AI systems to complex strategic planning frameworks. However, the StarCraft II platform, which has been widely adopted for validating decision-making algorithms in the past decade, has not yet provided substantial support for this emerging domain. To address issues that LLMs cannot interface with the hundreds of actions of the pysc2 backend and the lack of native support for multi-agent (MA) collaboration, we propose the LLM-PySC2 environment. This is the first environment that offers LLMs the complete pysc2 action space with sufficient multi-modal information and game Wiki knowledge. With an asynchronous query architecture, the environment efficiently interacts with LLMs that maintain a constant latency regardless of the scale of the agents' population. In the experiments, we evaluated LLMs' decision-making performance in both the macro-decision and micro-operation scenarios, with traditional StarCraft II Multi-Agent Challenge (SMAC) tasks and a series of new proposed. Results indicate that LLMs possess the potential to achieve victories in complex scenarios but cannot constantly generate correct decisions, especially in the recovered pysc2 action space and MA settings. Without task-relevant instructions, the pre-trained models suffer from issues such as hallucinations and inefficient collaboration. Our findings suggest that StarCraft II still challenges in the era of large models, revealing that there is a lot to do to develop an advanced LLM decision-making system, and the proposed LLM-PySC2 environment will support future development of LLM-based decision-making solutions.

Yehang Zhang, Xinli Xu, Xiaojie Xu et al.

Video-to-audio synthesis, which generates synchronized audio for visual content, critically enhances viewer immersion and narrative coherence in film and interactive media. However, video-to-audio dubbing for long-form content remains an unsolved challenge due to dynamic semantic shifts, temporal misalignment, and the absence of dedicated datasets. While existing methods excel in short videos, they falter in long scenarios (e.g., movies) due to fragmented synthesis and inadequate cross-scene consistency. We propose LVAS-Agent, a novel multi-agent framework that emulates professional dubbing workflows through collaborative role specialization. Our approach decomposes long-video synthesis into four steps including scene segmentation, script generation, sound design and audio synthesis. Central innovations include a discussion-correction mechanism for scene/script refinement and a generation-retrieval loop for temporal-semantic alignment. To enable systematic evaluation, we introduce LVAS-Bench, the first benchmark with 207 professionally curated long videos spanning diverse scenarios. Experiments demonstrate superior audio-visual alignment over baseline methods. Project page: https://lvas-agent.github.io

Xiaojie Xu, Xinli Xu, Sirui Chen et al.

Visual presentations are vital for effective communication. Early attempts to automate their creation using deep learning often faced issues such as poorly organized layouts, inaccurate text summarization, and a lack of image understanding, leading to mismatched visuals and text. These limitations restrict their application in formal contexts like business and scientific research. To address these challenges, we propose PreGenie, an agentic and modular framework powered by multimodal large language models (MLLMs) for generating high-quality visual presentations. PreGenie is built on the Slidev presentation framework, where slides are rendered from Markdown code. It operates in two stages: (1) Analysis and Initial Generation, which summarizes multimodal input and generates initial code, and (2) Review and Re-generation, which iteratively reviews intermediate code and rendered slides to produce final, high-quality presentations. Each stage leverages multiple MLLMs that collaborate and share information. Comprehensive experiments demonstrate that PreGenie excels in multimodal understanding, outperforming existing models in both aesthetics and content consistency, while aligning more closely with human design preferences.

Xiaojie Xu, Zongyuan Li, Chang Lu et al.

StarCraft II is a complex and dynamic real-time strategy (RTS) game environment, which is very suitable for artificial intelligence and reinforcement learning research. To address the problem of Large Language Model(LLM) learning in complex environments through self-reflection, we propose a Reflection of Episodes(ROE) framework based on expert experience and self-experience. This framework first obtains key information in the game through a keyframe selection method, then makes decisions based on expert experience and self-experience. After a game is completed, it reflects on the previous experience to obtain new self-experience. Finally, in the experiment, our method beat the robot under the Very Hard difficulty in TextStarCraft II. We analyze the data of the LLM in the process of the game in detail, verified its effectiveness.

Yuda Qiu, Xiaojie Xu, Lingteng Qiu et al.

Caricature is an artistic representation that deliberately exaggerates the distinctive features of a human face to convey humor or sarcasm. However, reconstructing a 3D caricature from a 2D caricature image remains a challenging task, mostly due to the lack of data. We propose to fill this gap by introducing 3DCaricShop, the first large-scale 3D caricature dataset that contains 2000 high-quality diversified 3D caricatures manually crafted by professional artists. 3DCaricShop also provides rich annotations including a paired 2D caricature image, camera parameters and 3D facial landmarks. To demonstrate the advantage of 3DCaricShop, we present a novel baseline approach for single-view 3D caricature reconstruction. To ensure a faithful reconstruction with plausible face deformations, we propose to connect the good ends of the detailrich implicit functions and the parametric mesh representations. In particular, we first register a template mesh to the output of the implicit generator and iteratively project the registration result onto a pre-trained PCA space to resolve artifacts and self-intersections. To deal with the large deformation during non-rigid registration, we propose a novel view-collaborative graph convolution network (VCGCN) to extract key points from the implicit mesh for accurate alignment. Our method is able to generate highfidelity 3D caricature in a pre-defined mesh topology that is animation-ready. Extensive experiments have been conducted on 3DCaricShop to verify the significance of the database and the effectiveness of the proposed method.